public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-03 04:51:24 +02:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: fix shared memory access condition for mmv (llama/10740)

Browse Source
This commit is contained in:
Johannes Gäßler
2024-12-18 12:52:16 +02:00
committed by Georgi Gerganov
parent a682fdce0c
commit eb27e0d834
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/mmv.cu
+1 -1
View File
@@ -57,7 +57,7 @@ static __global__ void mul_mat_vec(
if (block_size > WARP_SIZE) {
buf_iw[tid/WARP_SIZE] = sumf;
__syncthreads();
if (tid > WARP_SIZE) {
if (tid >= WARP_SIZE) {
return;
}
sumf = buf_iw[tid];